SuperGLUE

GPTKB entity

Statements (53)
Predicate Object
gptkbp:instanceOf gptkb:performance
gptkbp:assesses gptkb:Matthews_correlation_coefficient
F1 score
accuracy
gptkbp:containsTask gptkb:RTE
gptkb:COPA
gptkb:BoolQ
gptkb:AX-b
gptkb:MultiRC
gptkb:ReCoRD
gptkb:WiC
gptkb:WSC
CB
gptkbp:creator gptkb:Samuel_Bowman
gptkb:Alex_Wang
gptkb:Amanpreet_Singh
gptkb:Felix_Hill
gptkb:Julian_Michael
gptkb:Omer_Levy
gptkb:Nikita_Nangia
gptkb:Yada_Pruksachatkun
gptkbp:designedFor evaluating general language understanding
gptkbp:difficultyComparedToGLUE harder
gptkbp:domain gptkb:artificial_intelligence
natural language processing
gptkbp:fullName gptkb:Super_General_Language_Understanding_Evaluation
https://www.w3.org/2000/01/rdf-schema#label SuperGLUE
gptkbp:introducedIn 2019
gptkbp:language English
gptkbp:license gptkb:Apache_License_2.0
gptkbp:memiliki_tugas question answering
reading comprehension
coreference resolution
word sense disambiguation
natural language inference
gptkbp:notableModel gptkb:BART
gptkb:T5
gptkb:GPT-3
gptkb:ALBERT
gptkb:DeBERTa
gptkb:RoBERTa
gptkbp:notablePublication gptkb:SuperGLUE:_A_Stickier_Benchmark_for_General-Purpose_Language_Understanding_Systems
https://arxiv.org/abs/1905.00537
gptkbp:predecessor gptkb:GLUE
gptkbp:purpose benchmarking progress in language understanding
gptkbp:usedBy AI researchers
NLP practitioners
gptkbp:usedFor evaluating large language models
measuring generalization in NLP
gptkbp:website https://super.gluebenchmark.com/
gptkbp:bfsParent gptkb:GLUE
gptkb:DeBERTa
gptkbp:bfsLayer 6